Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    웰
    -0.07
    -mile
    -0.07
    估算
    -0.07
     manned
    -0.07
    和睦
    -0.07
     mücadele
    -0.07
     a
    -0.07
     embr
    -0.06
     GLuint
    -0.06
     FRE
    -0.06
    POSITIVE LOGITS
    UNCTION
    0.08
    .finish
    0.07
    altet
    0.07
     citizen
    0.07
    ости
    0.07
    TAIL
    0.07
    шло
    0.07
     categoria
    0.07
    인터
    0.07
     ostat
    0.06
    Act Density 0.004%

    No Known Activations